Jaehoon Lee

Artificial Intelligence · with Novak · 2014–2021

A researcher in the Science corpus: 11 papers; trusts 385 researchers and is trusted by 54 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 267 citations into it; #3,916 of 35,345 by trust here, #2,409 by citations
• Computer Vision and Pattern Recognition — 162 citations into it; #7,109 of 21,575 by trust here, #4,887 by citations
• Optimization & Training — 147 citations into it; #2,363 of 2,601 by trust here, #975 by citations
• Scaling & Learning Theory — 92 citations into it; #205 of 428 by trust here, #96 by citations
• Model Architectures — 68 citations into it; #710 of 2,278 by trust here, #635 by citations
• Statistical and Nonlinear Physics — 48 citations into it; #1,485 of 10,127 by trust here, #687 by citations
• Statistical Learning Theory — 43 citations into it
• Probabilistic & Bayesian Methods — 42 citations into it; #628 of 1,525 by trust here, #244 by citations

Whom Jaehoon Lee trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Alex Krizhevsky
2. Diederik P. Kingma
3. Geoffrey E. Hinton
4. Radford M. Neal
5. Yoshua Bengio
6. Kaiming He
7. Christopher K. I. Williams
8. Yann LeCun
9. Ilya Sutskever
10. Jimmy Ba

Who trusts Jaehoon Lee overall

1. Greg Yang
2. Timothy Nguyen
3. Soufiane Hayou
4. Daniel S. Park
5. Lechao Xiao
6. Roman Novak
7. Abdulkadir Canatar
8. Sanjeev Arora
9. Jascha Narain Sohl-Dickstein
10. Ethan Dyer

Papers from Jaehoon Lee's perspective

Ordered by how strongly the researchers Jaehoon Lee trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 citations
• Deep Neural Networks as Gaussian Processes (2017) — 1,255 citations
• Measuring the Effects of Data Parallelism on Neural Network Training (2018) — 484 citations
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (2018) — 331 citations
• Explaining neural scaling laws (2021) — 491 citations
• Dataset Meta-Learning from Kernel Ridge-Regression (2020) — 326 citations
• Dataset Distillation with Infinitely Wide Convolutional Networks (2021) — 307 citations
• Neural Tangents: Fast and Easy Infinite Neural Networks in Python (2019) — 261 citations
• On Empirical Comparisons of Optimizers for Deep Learning (2019) — 304 citations
• On the infinite width limit of neural networks with a standard parameterization (2020) — 56 citations
• Exact correlators of BPS Operators from the 3d superconformal bootstrap (2014) — 151 citations